OWL (Web Ontology Language) ontologies, which are able to represent both relational and type facts as standard knowledge graphs and complex domain knowledge in Description Logic (DL) axioms, are widely adopted in domains such as healthcare and bioinformatics. Inspired by the success of knowledge graph embeddings, embedding OWL ontologies has gained significant attention in recent years. Current methods primarily focus on learning embeddings for atomic concepts and roles, enabling the evaluation based on normalized axioms through specially designed score functions. However, they often neglect the embedding of complex concepts, making it difficult to infer with more intricate axioms. This limitation reduces their effectiveness in advanced reasoning tasks, such as Ontology Learning and ontology-mediated Query Answering. In this paper, we propose EL++-closed ontology embeddings which are able to represent any logical expressions in DL EL++ via composition. Furthermore, we develop TransBox, an effective EL++ -closed ontology embedding method that can handle many-to-one, one-to-many and many-to-many relations. Our extensive experiments demonstrate that TransBox often achieves state-of-the-art performance across various real-world datasets for predicting complex axioms.
论文检索
输入标题、作者或关键词，从 447 篇学术成果中精准定位
Graphs have emerged as a foundation for a variety of applications, including capturing factual knowledge, semantic data integration, social networks, and informing machine learning algorithms. Formalising properties of the data and ensuring data quality requires describing schemas of such graphs. Driven by diverse applications, the Semantic Web and database communities developed not only different graph data models-RDF and property graphs-but also different graph schema languages-SHACL, ShEx, and PG-Schema. Each language has its unique approach to defining constraints and validating graph data, leaving potential users in the dark about their commonalities and differences. In this paper, we provide concise formal definitions of the core components of these languages, employ a uniform framework to facilitate a comprehensive comparison between them, and identify a common set of functionalities, shedding light on both overlapping and distinctive features.
In 2024, Demis Hassabis and John Jumper won the Nobel Prize for Chemistry for developing an AI model to predict the shape of every protein known to mankind. Chair of the Nobel Committee, Heiner Linke, described the AI system as the achievement of a ''50-year-old dream'' that solved a notoriously difficult problem eluding scientists since the 1970s. This AI system, AlphaFold, has ushered in a golden age of AI for science - the development of AI techniques for accelerating scientific discovery. We are currently amid the largest surge in the application and development of AI for scientific research in history. Scholarly publications, patents, education, training, research activity and investment are increasing at unprecedented rates. AI may help scientists address humanity's greatest challenges such as climate change, pollution, resource scarcity and infectious diseases. In this talk, I will cover the state of practice in AI for science. I'll discuss some of the successes already achieved as well as challenges for applying AI to science in the future. And I'll highlight some of the work at CSIRO, Australia's national science agency, which contains over 1000 AI experts developing novel AI solutions to long-standing scientific problems.
Recent advancements in deep learning and artificial intelligence have driven significant progress in time series modeling and analysis. On one hand, researchers seek breakthroughs in performance on classical tasks such as forecasting, anomaly detection, classification, etc. On the other hand, it is intriguing to explore the potential for answering more complex inference and reasoning tasks from time series. In this keynote, I will examine the pathways toward foundation models for time series and discuss future research directions in this rapidly evolving field. The remarkable success of foundation models in natural language processing - exemplified by Generative Pre-trained Transformers (GPT) - suggests their potential to revolutionize time series analysis. I will introduce our recent efforts along this direction, including TEMPO, a novel framework designed to learn effective time series representations by leveraging two key inductive biases: one is explicit decomposition of trend, seasonal, and residual components, and the second is prompt-based distribution adaptation for diverse time series types. Beyond representation learning, practical applications demands advanced reasoning capabilities with multi-step time series inference task, requiring both compositional reasoning and computational precision. To tackle this challenge, I will discuss TS-reasoner, a program-aided inference agent that integrates large language models (LLMs) with structured execution pipelines, in-context learning, and self-correction mechanisms. I will discuss a new benchmark dataset and evaluation framework to systematically assess multi-step time series reasoning. By bridging deep learning advances with structured reasoning, I will highlight the next frontier in time series research, i.e., developing foundation models that enhance forecasting performance, generative models, and reasoning capabilities from time series across diverse applications.
As a revolutionary pre-training model, ChatGPT has already had a huge impact on global economic. It is the strong foundation of computing power that enables large models to continuously improve in the process of understanding massive data, resulting in breakthrough innovations. Based on the Peng Cheng Cloud Brain II E-level intelligent computing platform, Peng Cheng Laboratory is training PCL Mind Series of Large Model. Mind is the first fully autonomous, controllable, safe, open-source pre-training foundation model in China, where the performance of the 200 billion parameter base model reaches the international advanced, and the output content conforms to the Chinese core values. Peng Cheng Laboratory is opening up PCL Mind cooperation and work with external partners to continuously build a large model open-source consortium for domestic large model ecosystem. The next generation-Peng Cheng Cloud Brain III will break through key technologies such as high computing power chips, large-scale networking communication, high-performance software stacks, and large-scale parallel training, and support 10,000 chip-level parallel training of trillion-level parameter AI.
The web is the world's largest knowledge repository, yet as AI systems become increasingly integrated into our digital infrastructure, the ability to retrieve, reason, and collaborate effectively has become paramount. Large Language Models (LLMs) are evolving from passive responders to active knowledge agents that can retrieve complex information, validate hypotheses, and optimize interactions over multiple turns. In this talk, I will explore the frontiers of AI-driven knowledge retrieval and reasoning, drawing from recent research on knowledge graphs, semi-structured retrieval, adaptive tool use, and multi-turn AI collaboration. I will also discuss how agentic frameworks enable rigorous, automated hypothesis validation through sequential falsifications. Together, these advancements push beyond traditional search and QA systems, unlocking new capabilities for knowledge discovery, scientific research, and human-AI collaboration. Finally, I will highlight key challenges and opportunities in building AI systems that are not just accurate, but also interactive, explainable, and aligned with human needs.
Around 1990, the Berlin Wall came down, the WWW was born at CERN, mobile phones became popular, self-driving cars appeared in traffic, and modern AI based on very deep artificial neural networks emerged, including the principles behind the G, P, and T in ChatGPT. I place these events in the history of the universe since the Big Bang, and discuss what's next: not just AI behind the screen in the virtual world, but real AI for real robots in the real world, connected through a WWW of machines. Intelligent (but not necessarily super-intelligent) robots that can learn to operate the tools and machines operated by humans can also build (and repair when needed) more of their own kind. This will culminate in life-like, self-replicating and self-improving machine civilisations, which represent the ultimate form of upscaling, and will shape the long-term future of the entire cosmos. The wonderful short-term side effect is that our AI will continue to make people's lives longer, healthier and easier.